CN109855624A - Navigation device and air navigation aid for AGV vehicle - Google Patents
Navigation device and air navigation aid for AGV vehicle Download PDFInfo
- Publication number
- CN109855624A CN109855624A CN201910051092.9A CN201910051092A CN109855624A CN 109855624 A CN109855624 A CN 109855624A CN 201910051092 A CN201910051092 A CN 201910051092A CN 109855624 A CN109855624 A CN 109855624A
- Authority
- CN
- China
- Prior art keywords
- agv vehicle
- image
- fpga chip
- chip system
- navigation device
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to a kind of navigation devices and air navigation aid for AGV vehicle, wherein the navigation device for AGV vehicle includes: laser radar (1), for obtaining the planar information of AGV vehicle local environment；Imaging sensor (2), for acquiring the external environment image of the AGV vehicle；Fpga chip system (3), connect respectively with the laser radar (1) and described image sensor (2), for receive the laser radar (1) planar information and described image sensor (2) external environment image and handled.Navigation device for AGV vehicle of the invention, laser radar, imaging sensor and fpga chip system are combined as a whole, and Attribute Recognition is carried out to the object in environment in such a way that image, semantic is divided, it is effectively guaranteed the accuracy of identification and recognition speed of object, to guarantee the navigation accuracy for AGV vehicle.
Description
Technical field
The present invention relates to robot navigation's technical field more particularly to a kind of navigation devices and navigation side for AGV vehicle
Method.
Background technique
AGV mobile robot is robot work in industrial environment, with contexture by self, based on laser slam's
AGV can obtain indoor environmental information, obtain environment letter in real time by sensor in moving process by constructing indoor map
Breath, determines position of the AGV robot in ambient enviroment to carry out the matching of position with known map match.
Although laser radar slam navigation is navigation system common at present, laser radar slam navigation system is often
By combine RGB-D auxiliary camera (3-dimensional image sensor) use, mainly for three-dimensional environment carry out characteristic point extraction and
Compare.But in the scene of certain features, such as in the more scene of gallery, blank wall, characteristic point is unobvious, the above method
Will lead to characteristic point extraction matching it is easy to appear deviation even mistake.Meanwhile features described above point extracts, at matched mode
Reason get up it is relative complex, serious forgiveness is low, and precision not can guarantee.In addition, existing s lam navigation system is using industrial personal computer system
System, power consumption and volume are larger, and power dissipation ratio of performance is low.
Summary of the invention
The purpose of the present invention is to provide a kind of navigation device and air navigation aid for AGV vehicle, improve navigation accuracy and
Arithmetic speed.
To achieve the above object, the present invention provides a kind of navigation device of AGV vehicle, comprising:
Laser radar, for obtaining the planar information of AGV vehicle local environment；
Imaging sensor, for acquiring the external environment image of the AGV vehicle；
Fpga chip system is connect with the laser radar and described image sensor respectively, for receiving the laser
The planar information of radar and the external environment image of described image sensor are simultaneously handled.
According to an aspect of the present invention, the fpga chip system is also used to obtain the location point of the AGV vehicle.
According to an aspect of the present invention, the planar that the fpga chip system obtains the laser radar
The processing of information includes that the building of the AGV vehicle local environment two-dimensional surface map is carried out according to the planar information.
According to an aspect of the present invention, the outside that the fpga chip system acquires described image sensor
The processing of ambient image includes that the various objects in the external environment image are carried out with Attribute Recognition and is labeled.
According to an aspect of the present invention, using image, semantic cutting techniques to each object in the external environment image
Body carries out Attribute Recognition and is labeled respectively.
According to an aspect of the present invention, described image sensor is the optical camera that can obtain flat image.
The present invention also provides a kind of air navigation aids using the above-mentioned navigation device for AGV vehicle, comprising:
S1, fpga chip system are according to the two-dimensional surface of AGV vehicle local environment described in the planar information architecture
Figure；
S2, fpga chip system carry out image, semantic segmentation to the external environmental information, to the external environment image
In each object carry out Attribute Recognition；
S3, by each object matches after Attribute Recognition in the external environment image into the two-dimensional surface map, obtain
To position of each object in the two-dimensional surface map；
S4, position of the AGV vehicle in the two-dimensional surface map is obtained by fpga chip system, and in conjunction with described
The position of each object in two-dimensional surface map obtained in S3 carries out optimal path and plans automatically.
Navigation device for AGV vehicle of the invention, laser radar, imaging sensor and fpga chip system are combined into
One, and Attribute Recognition is carried out to the object in environment in such a way that image, semantic is divided, it is effectively guaranteed the knowledge of object
Other precision and recognition speed, to guarantee the navigation accuracy for AGV vehicle.
Navigation device for AGV vehicle of the invention is to ring due to the mode using image, semantic dividing processing
Various objects in border carry out Attribute Recognition, so in the present invention, imaging sensor (can be shot using general camera
The optical camera of two dimensional image).Using RGB-D camera (3-dimensional image sensor) to object in compared with the prior art
For geometry identification, the mode of Attribute Recognition is more accurate to the extraction and cognition of object.General camera generation is utilized simultaneously
It is simple and convenient for RGB-D camera in the prior art.
In the present invention, due to using fpga chip system, Image Information Processing is integrated with fpga chip system, mentions
Greatly reduce system overall volume while rising system overall stability, not needing industrial personal computer processing can be directly defeated
The information such as map, position out, for the high energy consumption of industrial computer system, large volume, the present invention can be effectively reduced power consumption,
Reduce volume.In addition, the present invention takes full advantage of the parallel high-speed processing capacity of fpga chip, advanced complex process ability, it is complete
At can be realized the real-time slam of AGV vehicle, compared with the prior art for, greatly reduce error probability, advantageously ensure that and lead
Boat precision, while efficiency being provided.
Detailed description of the invention
Fig. 1 schematically shows the structure composition diagram of the navigation device according to the present invention for AGV vehicle.
Specific embodiment
It, below will be to embodiment in order to illustrate more clearly of embodiment of the present invention or technical solution in the prior art
Needed in attached drawing be briefly described.It should be evident that the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skills without creative efforts, can also be according to these
Attached drawing obtains other attached drawings.
When being described for embodiments of the present invention, term " longitudinal direction ", " transverse direction ", "upper", "lower", " preceding ",
" rear ", "left", "right", "vertical", "horizontal", "top", "bottom" "inner", orientation or positional relationship expressed by "outside" are based on phase
Orientation or positional relationship shown in the drawings is closed, is merely for convenience of description of the present invention and simplification of the description, rather than instruction or dark
Show that signified device or element must have a particular orientation, be constructed and operated in a specific orientation, therefore above-mentioned term cannot
It is interpreted as limitation of the present invention.
The present invention is described in detail with reference to the accompanying drawings and detailed description, embodiment cannot go to live in the household of one's in-laws on getting married one by one herein
It states, but therefore embodiments of the present invention are not defined in following implementation.
As shown in Figure 1, a kind of embodiment according to the present invention, the navigation device for AGV of the invention includes laser
Radar 1, imaging sensor 2 and fpga chip system 3.Laser radar 1 and imaging sensor 2 respectively with 3 phase of fpga chip system
Connection, laser radar 1 and imaging sensor 2 can be connected with each other by Ethernet or USB and fpga chip system 3.Wherein
Laser radar 1 is used to the planar information of AGV vehicle local environment being transferred to fpga chip system 3, and imaging sensor 2 is used for
It acquires the external environment image of AGV vehicle and is transmitted to fpga chip system 3, fpga chip system 3 is for receiving above- mentioned information simultaneously
It is handled.In addition, fpga chip system of the invention is also used to obtain the position of AGV vehicle, and combine the place to information data
Reason is as a result, realize the navigation feature to AGV vehicle.
Specifically, the processing for the planar information that fpga chip system 3 obtains laser radar 1 includes according to plane
Building of the two-dimensional signal to AGV vehicle local environment two-dimensional surface map.Specifically, along the circumferential direction 360 ° of laser radar 1
Every ray represents different range informations, constructs two-dimensional surface map according to this different distance information system obtained.
Fpga chip system 3 includes to external ambient image to the processing for the external environment image that imaging sensor 2 acquires
In various objects Attribute Recognition and be labeled.Specifically, in the present invention, using image, semantic segmentation by the way of pair
Each object in external environment image carries out Attribute Recognition.Image, semantic cutting techniques are a kind of modes to image procossing,
Multiple semantic classes, such as area of feasible solutions, infeasible region, barrier and people etc. are mainly established, pass through real-time reception later
The image taken is marked identification to each of image pixel, is determined in image according to attributes such as unity and coherence in writing, brightness
Classification belonging to each pixel (area of feasible solutions, infeasible region, barrier and people).
Navigation device for AGV vehicle of the invention is to ring due to the mode using image, semantic dividing processing
Various objects in border carry out Attribute Recognition, so in the present invention, imaging sensor 2 can (energy using general camera
Enough shoot the optical camera of two dimensional image).It is right using RGB-D camera (3-dimensional image sensor) in compared with the prior art
For the geometry identification of object, the mode of Attribute Recognition is more accurate to the extraction and cognition of object.Simultaneously using common
Camera replaces RGB-D camera in the prior art, simple and convenient.
The air navigation aid of navigation device for AGV vehicle of the invention is as follows: S1, fpga chip system are according to planar
The two-dimensional surface map of information architecture AGV vehicle local environment；S2, fpga chip system external portion's environmental information carry out image, semantic
Segmentation carries out Attribute Recognition to object each in external ambient image；S3, by each object after Attribute Recognition in external environment image
It is matched in two-dimensional surface map, obtains position of each object in the two-dimensional surface map；S4, pass through fpga chip system
Position of the AGV vehicle in two-dimensional surface map is obtained, and combines the position of each object in the two-dimensional surface map obtained in S3
Optimal path is carried out to plan automatically.
It generally speaking, is the building for combining laser radar 1 to carry out environment two-dimensional surface map by fpga chip system 3,
Fpga chip system 3 combines the external ambient images of 2 pairs of imaging sensor to carry out semantic segmentation processing later, in environment into
Position in the object matches of row image, semantic segmentation to each comfortable two-dimensional surface map generated based on laser radar 1, in this way
After each imaging sensor 2 obtains environmental objects progress semantics recognition, so that it may know that it is generated relative to based on laser radar
Two-dimensional surface map on position.Then by fpga chip system 3 the position and attitude point and environment semanteme minute of AGV vehicle
Each object for cutting acquisition is labeled in configuration node on two-dimensional surface map, and composition optimizes constraint condition, and passes through figure optimization
Method obtain degree of precision the position AGV and various bad border object spaces, to AGV vehicle carry out trajectory path planning.
Navigation device for AGV vehicle of the invention, by 3 knot of laser radar 1, imaging sensor 2 and fpga chip system
It is integrated, and Attribute Recognition is carried out to the object in environment in such a way that image, semantic is divided, be effectively guaranteed object
Accuracy of identification and recognition speed, thus guarantee for AGV vehicle navigation accuracy.
In addition, in the present invention, due to using fpga chip system 3, Image Information Processing is integrated and fpga chip system
In system 3, lifting system overall stability while, greatly reduces system overall volume, and not needing industrial personal computer processing can
The information such as enough direct output map, position, for the high energy consumption of industrial computer system, large volume, the present invention can be effective
It reduces power consumption, reduce volume.In addition, the present invention take full advantage of fpga chip parallel high-speed processing capacity, it is advanced complexity at
Reason ability, completion can be realized the real-time slam of AGV vehicle, compared with the prior art for, greatly reduce error probability, favorably
In guarantee navigation accuracy, while providing efficiency.
The foregoing is merely a schemes of the invention, are not intended to restrict the invention, for the technology of this field
For personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (7)
1. a kind of navigation device for AGV vehicle characterized by comprising
Laser radar (1), for obtaining the planar information of AGV vehicle local environment；
Imaging sensor (2), for acquiring the external environment image of the AGV vehicle；
Fpga chip system (3) is connect with the laser radar (1) and described image sensor (2) respectively, described for receiving
The planar information of laser radar (1) and the external environment image of described image sensor (2) are simultaneously handled.
2. the navigation device according to claim 1 for AGV vehicle, which is characterized in that the fpga chip system (3) is also
For obtaining the location point of the AGV vehicle.
3. the navigation device according to claim 1 for AGV vehicle, which is characterized in that the fpga chip system (3) is right
The processing for the planar information that the laser radar (1) obtains includes according to described in planar information progress
The building of AGV vehicle local environment two-dimensional surface map.
4. the navigation device according to claim 1 for AGV vehicle, which is characterized in that the fpga chip system (3) is right
In the processing of the external environment image of described image sensor (2) acquisition include to various in the external environment image
Object carries out Attribute Recognition and is labeled.
5. the navigation device according to claim 4 for AGV vehicle, which is characterized in that use image, semantic cutting techniques
Attribute Recognition is carried out to each object in the external environment image and is labeled respectively.
6. the navigation device according to claim 1 for AGV vehicle, which is characterized in that described image sensor (2) is energy
Enough obtain the optical camera of flat image.
7. a kind of air navigation aid using the navigation device for being used for AGV vehicle described in claim 1-6, comprising:
The two-dimensional surface map of S1, fpga chip system according to AGV vehicle local environment described in the planar information architecture；
S2, fpga chip system carry out image, semantic segmentation to the external environmental information, to each in the external environment image
Object carries out Attribute Recognition；
S3, by each object matches after Attribute Recognition in the external environment image into the two-dimensional surface map, obtain institute
State position of each object in the two-dimensional surface map；
S4, position of the AGV vehicle in the two-dimensional surface map is obtained by fpga chip system, and in conjunction in the S3
The position of each object in the two-dimensional surface map of acquisition carries out optimal path and plans automatically.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910051092.9A CN109855624A (en) | 2019-01-17 | 2019-01-17 | Navigation device and air navigation aid for AGV vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910051092.9A CN109855624A (en) | 2019-01-17 | 2019-01-17 | Navigation device and air navigation aid for AGV vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109855624A true CN109855624A (en) | 2019-06-07 |
Family
ID=66895208
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910051092.9A Pending CN109855624A (en) | 2019-01-17 | 2019-01-17 | Navigation device and air navigation aid for AGV vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109855624A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111781929A (en) * | 2020-07-08 | 2020-10-16 | 苏州索亚机器人技术有限公司 | AGV trolley and 3D laser radar positioning and navigation method |
| CN112130555A (en) * | 2020-06-09 | 2020-12-25 | 广东科学技术职业学院 | Self-walking robot and system based on laser navigation radar and computer vision perception fusion |
| CN112308076A (en) * | 2020-10-30 | 2021-02-02 | 山东华锐智能技术有限公司 | Multi-semantic safety map construction, use and scheduling method for AGV navigation scheduling |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150138310A1 (en) * | 2013-11-19 | 2015-05-21 | Nokia Corporation | Automatic scene parsing |
| CN106780735A (en) * | 2016-12-29 | 2017-05-31 | 深圳先进技术研究院 | A kind of semantic map constructing method, device and a kind of robot |
| CN106802954A (en) * | 2017-01-18 | 2017-06-06 | 中国科学院合肥物质科学研究院 | Unmanned vehicle semanteme cartographic model construction method and its application process on unmanned vehicle |
| CN107063258A (en) * | 2017-03-07 | 2017-08-18 | 重庆邮电大学 | A kind of mobile robot indoor navigation method based on semantic information |
| CN108776474A (en) * | 2018-05-24 | 2018-11-09 | 中山赛伯坦智能科技有限公司 | Robot embedded computing terminal integrating high-precision navigation positioning and deep learning |
| CN108920584A (en) * | 2018-06-25 | 2018-11-30 | 广州视源电子科技股份有限公司 | A kind of semanteme grating map generation method and its device |
| CN208224794U (en) * | 2018-05-24 | 2018-12-11 | 中山赛伯坦智能科技有限公司 | Robot terminal device |
-
2019
- 2019-01-17 CN CN201910051092.9A patent/CN109855624A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150138310A1 (en) * | 2013-11-19 | 2015-05-21 | Nokia Corporation | Automatic scene parsing |
| CN106780735A (en) * | 2016-12-29 | 2017-05-31 | 深圳先进技术研究院 | A kind of semantic map constructing method, device and a kind of robot |
| CN106802954A (en) * | 2017-01-18 | 2017-06-06 | 中国科学院合肥物质科学研究院 | Unmanned vehicle semanteme cartographic model construction method and its application process on unmanned vehicle |
| CN107063258A (en) * | 2017-03-07 | 2017-08-18 | 重庆邮电大学 | A kind of mobile robot indoor navigation method based on semantic information |
| CN108776474A (en) * | 2018-05-24 | 2018-11-09 | 中山赛伯坦智能科技有限公司 | Robot embedded computing terminal integrating high-precision navigation positioning and deep learning |
| CN208224794U (en) * | 2018-05-24 | 2018-12-11 | 中山赛伯坦智能科技有限公司 | Robot terminal device |
| CN108920584A (en) * | 2018-06-25 | 2018-11-30 | 广州视源电子科技股份有限公司 | A kind of semanteme grating map generation method and its device |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112130555A (en) * | 2020-06-09 | 2020-12-25 | 广东科学技术职业学院 | Self-walking robot and system based on laser navigation radar and computer vision perception fusion |
| CN112130555B (en) * | 2020-06-09 | 2023-09-15 | 广东科学技术职业学院 | Self-walking robot and system based on laser navigation radar and computer vision perception fusion |
| CN111781929A (en) * | 2020-07-08 | 2020-10-16 | 苏州索亚机器人技术有限公司 | AGV trolley and 3D laser radar positioning and navigation method |
| CN112308076A (en) * | 2020-10-30 | 2021-02-02 | 山东华锐智能技术有限公司 | Multi-semantic safety map construction, use and scheduling method for AGV navigation scheduling |
| CN112308076B (en) * | 2020-10-30 | 2023-05-30 | 济南蓝图士智能技术有限公司 | Multi-semantic safety map construction, use and scheduling method for AGV navigation scheduling |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108827306B (en) | Unmanned aerial vehicle SLAM navigation method and system based on multi-sensor fusion | |
| CN109509230A (en) | A kind of SLAM method applied to more camera lens combined type panorama cameras | |
| CN102419178B (en) | Mobile robot positioning system and method based on infrared road sign | |
| CN102426019B (en) | Unmanned aerial vehicle scene matching auxiliary navigation method and system | |
| CN109855624A (en) | Navigation device and air navigation aid for AGV vehicle | |
| Yue et al. | A hierarchical framework for collaborative probabilistic semantic mapping | |
| CN112184812B (en) | Method for improving identification and positioning precision of unmanned aerial vehicle camera to april tag and positioning method and system | |
| CN113625774B (en) | Local map matching and end-to-end ranging multi-unmanned aerial vehicle co-location system and method | |
| Li et al. | Automatic targetless LiDAR–camera calibration: a survey | |
| CN110533716A (en) | A kind of semantic SLAM system and method based on 3D constraint | |
| Qian et al. | Wearable-assisted localization and inspection guidance system using egocentric stereo cameras | |
| Li et al. | Multiple RGB-D sensor-based 3-D reconstruction and localization of indoor environment for mini MAV | |
| Razali et al. | Visual simultaneous localization and mapping: a review | |
| He et al. | Visual positioning system for small-scaled spherical robot in underwater environment | |
| Dai et al. | A Review of Common Techniques for Visual Simultaneous Localization and Mapping | |
| Li et al. | Collaborative positioning for swarms: A brief survey of vision, LiDAR and wireless sensors based methods | |
| Zhang et al. | Hybrid iteration and optimization-based three-dimensional reconstruction for space non-cooperative targets with monocular vision and sparse lidar fusion | |
| Lin et al. | Vision aided motion estimation for unmanned helicopters in GPS denied environments | |
| Li et al. | A Research of Visual-Inertial Simultaneous Localization and Mapping | |
| Ye et al. | 3D Surfel Map-Aided Visual Relocalization with Learned Descriptors | |
| Fu et al. | Costmap construction and pseudo-lidar conversion method of mobile robot based on monocular camera | |
| Song et al. | FHT-Map: Feature-based Hybrid Topological Map for Relocalization and Path Planning | |
| Liu et al. | A Review of Sensing Technologies for Indoor Autonomous Mobile Robots | |
| Fu et al. | A Lightweight Autonomous Vehicle System Based On Pure Visual Navigation | |
| Du et al. | GNSS-Assisted LiDAR Odometry and Mapping for Urban Environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190607 |
|
| RJ01 | Rejection of invention patent application after publication |